大模型能否理解分子空间约束？这篇论文首次系统评估了LLM在分子结合任务中的表现，跨界AI与科学计算的新奇尝试。
arXiv:2607.18144v1 Announce Type: cross Abstract: Structure-based drug design (SBDD) leverages the 3D structure of protein targets, often complemented…
专为AI4Science安全设计，从风险维度量化评估科学AI的潜在隐患，填补该领域基准空白。
arXiv:2606.18936v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly embedded in AI for Science (AI4Science) workflows, from …
用AI模拟海洋，破解跨分辨率难题，Samudra 2带来高效仿真新突破
arXiv:2606.02610v1 Announce Type: cross Abstract: Ocean general circulation models (OGCMs) are essential to climate science but computationally expens…
原创博士级科学基准，专测LLM在扫描探针显微镜领域的专业能力。
arXiv:2602.22971v2 Announce Type: replace Abstract: As LLMs achieved breakthroughs in general reasoning, their proficiency in specialized scientific d…
用LLM智能体玩转电池参数逆估计，把复杂数值模拟交给AI，效率拉满！
arXiv:2605.29560v1 Announce Type: new Abstract: Parameterizing high-fidelity "digital twins" of batteries is a critical yet challenging inverse proble…
稀疏自编码器首次建立大脑皮层语义拓扑与LLM特征的可解释映射，跨学科新突破
Article URL: https://letsdatascience.com/news/sparse-autoencoders-reveal-cortical-brain-llm-semantic-mappi-bc586635 Comments URL: https://news.ycombin…
用严谨的数学指标审计科学AI模型内部结构，避免模型依靠数据捷径而非真正科学规律。
arXiv:2605.21731v1 Announce Type: new Abstract: Deep learning models are increasingly used in scientific prediction tasks where strong benchmark perfo…
用大模型代理模拟专家思维，从红外光谱精准推断化学结构，AI+化学新突破。
arXiv:2508.16112v2 Announce Type: replace Abstract: Spectral analysis provides crucial clues for the elucidation of unknown materials. Among various t…
SandboxAQ把药物发现模型搬进Claude，对话界面让科研门槛骤降，不用博士级算力也能搞分子研究。
Other venture-backed companies like Chai Discovery and Isomorphic Labs have raced to build better models. SandboxAQ is betting that access is the bigg…